Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 20983
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations, specifically places with the suffix "-lia" or containing the string "lio"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographical locations, particularly 'lia' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spoiled
    -0.68
     Category
    -0.63
     save
    -0.62
     AK
    -0.61
     buck
    -0.60
     caps
    -0.60
     DEAD
    -0.59
     marks
    -0.59
     Expansion
    -0.59
     Quran
    -0.59
    POSITIVE LOGITS
    lia
    4.73
    lio
    2.52
    lie
    1.49
    li
    1.44
    liam
    1.27
    lis
    1.20
    bia
    1.20
    lov
    1.14
    la
    1.13
     lia
    1.13
    Activations Density 0.013%

    No Known Activations